| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| Intermediate Dataset original corpus labels (test) | Precision99.5 | 9 | 8d ago | ||
| WhoSaidIt re-annotated (test) | Male Accuracy91.9 | 8 | 8d ago | ||
| WhoSaidIt Pooled Languages public release | GPT-4.1 | Accuracy (Male)92 | 1 | 8d ago | |
| WhoSaidIt Chinese public release | GPT-4.1 | Accuracy (Male)94.9 | 1 | 8d ago | |
| WhoSaidIt Korean public release subset | GPT-4.1 | Male Accuracy89.9 | 1 | 8d ago | |
| WhoSaidIt Italian public release | GPT-4.1 | Attribute Accuracy: Male87.9 | 1 | 8d ago | |
| WhoSaidIt Spanish public release | GPT-4.1 | Accuracy (Male)87 | 1 | 8d ago | |
| WhoSaidIt English public release | GPT-4.1 | Accuracy (Male)100 | 1 | 8d ago |
